Advanced Lane Finding Project¶
The goals / steps of this project are the following:
- Compute the camera calibration matrix and distortion coefficients given a set of chessboard images.
- Apply a distortion correction to raw images.
- Use color transforms, gradients, etc., to create a thresholded binary image.
- Apply a perspective transform to rectify binary image ("birds-eye view").
- Detect lane pixels and fit to find the lane boundary.
- Determine the curvature of the lane and vehicle position with respect to center.
- Warp the detected lane boundaries back onto the original image.
- Output visual display of the lane boundaries and numerical estimation of lane curvature and vehicle position.
First, I'll compute the camera calibration using chessboard images¶
In [182]:
import numpy as np
import cv2
import glob
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from matplotlib.path import Path
import matplotlib.patches as patches
%matplotlib inline
# prepare object points, like (0,0,0), (1,0,0), (2,0,0) ....,(6,5,0)
objp = np.zeros((6*9,3), np.float32)
objp[:,:2] = np.mgrid[0:9,0:6].T.reshape(-1,2)
# Arrays to store object points and image points from all the images.
objpoints = [] # 3d points in real world space
imgpoints = [] # 2d points in image plane.
# Make a list of calibration images
images = glob.glob('camera_cal/calibration*.jpg')
images_with_chessboard_corners = []
# Step through the list and search for chessboard corners
for fname in images:
img = cv2.imread(fname)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# Find the chessboard corners
ret, corners = cv2.findChessboardCorners(gray, (9,6),None)
# If found, add object points, image points
if ret == True:
objpoints.append(objp)
imgpoints.append(corners)
# Draw and display the corners
img = cv2.drawChessboardCorners(img, (9,6), corners, ret)
images_with_chessboard_corners.append(img)
# Horizontal layout
# https://stackoverflow.com/questions/19471814/display-multiple-images-in-one-ipython-notebook-cell
plt.figure(figsize=(50,30))
columns = 4
for i, image in enumerate(images_with_chessboard_corners):
plt.subplot(len(images_with_chessboard_corners) / columns + 1, columns, i + 1)
plt.imshow(image)
Then I will compute camera calibration matrix and distortion coefficients¶
In [183]:
def cal_undistort(img, objpoints, imgpoints):
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#ret, corners = cv2.findChessboardCorners(gray, (8,6), None)
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpoints, imgpoints, gray.shape[::-1], None, None)
undist = cv2.undistort(img, mtx, dist, None, mtx)
return undist
def plot_two_images(img1, img2, modified_image_text="Undistorted Image"):
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(cv2.cvtColor(img1, cv2.COLOR_BGR2RGB))
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(cv2.cvtColor(img2, cv2.COLOR_BGR2RGB))
ax2.set_title(modified_image_text, fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
Let's display a few of the chessboard images, but undistorted¶
In [184]:
# Display a few images
img = cv2.imread('camera_cal/calibration19.jpg')
plot_two_images(img, cal_undistort(img, objpoints, imgpoints))
img = cv2.imread('camera_cal/calibration1.jpg')
plot_two_images(img, cal_undistort(img, objpoints, imgpoints))
img = cv2.imread('camera_cal/calibration10.jpg')
plot_two_images(img, cal_undistort(img, objpoints, imgpoints))
Looks good! Now let's apply the same undistortion to some of the test images¶
In [185]:
img = cv2.imread('test_images/test1.jpg')
plot_two_images(img, cal_undistort(img, objpoints, imgpoints))
img = cv2.imread('test_images/test2.jpg')
plot_two_images(img, cal_undistort(img, objpoints, imgpoints))
img = cv2.imread('test_images/test3.jpg')
plot_two_images(img, cal_undistort(img, objpoints, imgpoints))
In [187]:
def abs_sobel_thresh(img, orient='x', sobel_kernel=3, thresh_min=0, thresh_max=255):
# Apply the following steps to img
# 1) Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 2) Take the derivative in x or y given orient = 'x' or 'y'
if (orient == 'x'):
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
abs_sobel = np.absolute(sobelx)
if (orient == 'y'):
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
abs_sobel = np.absolute(sobely)
# 4) Scale to 8-bit (0 - 255) then convert to type = np.uint8
scaled_sobel = np.uint8(255*abs_sobel/np.max(abs_sobel))
# 5) Create a mask of 1's where the scaled gradient magnitude
# is > thresh_min and < thresh_max
binary_output = np.zeros_like(scaled_sobel)
binary_output[(scaled_sobel >= thresh_min) & (scaled_sobel <= thresh_max)] = 1
# 6) Return this mask as your binary_output image
#binary_output = np.copy(img) # Remove this line
return binary_output
def plot_threshold_gradient(img1, img2, label="Abs Sobel Threshold"):
# Plot the result
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(cv2.cvtColor(img1, cv2.COLOR_BGR2RGB))
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(img2, cmap='gray')
ax2.set_title(label, fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
image = cv2.imread('test_images/test1.jpg')
grad_binary = abs_sobel_thresh(image, orient='x', thresh_min=20, thresh_max=110)
plot_threshold_gradient(image, grad_binary)
image = cv2.imread('test_images/test2.jpg')
grad_binary = abs_sobel_thresh(image, orient='x', thresh_min=20, thresh_max=110)
plot_threshold_gradient(image, grad_binary)
image = cv2.imread('test_images/test3.jpg')
grad_binary = abs_sobel_thresh(image, orient='x', thresh_min=20, thresh_max=110)
plot_threshold_gradient(image, grad_binary)
Magnitude Threshold¶
In [188]:
def mag_thresh(img, sobel_kernel=3, mag_thresh=(0, 255)):
# Apply the following steps to img
# 1) Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
# 2) Take the gradient in x and y separately
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
# 3) Calculate the magnitude
abs_sobelx = np.absolute(sobelx)
abs_sobely = np.absolute(sobely)
gradmag = np.sqrt(sobelx**2 + sobely**2)
scale_factor = np.max(gradmag)/255
gradmag = (gradmag/scale_factor).astype(np.uint8)
# Create a binary image of ones where threshold is met, zeros otherwise
binary_output = np.zeros_like(gradmag)
binary_output[(gradmag >= mag_thresh[0]) & (gradmag <= mag_thresh[1])] = 1
return binary_output
image = cv2.imread('test_images/test3.jpg')
mag_binary = mag_thresh(image, sobel_kernel=3, mag_thresh=(30, 100))
plot_threshold_gradient(image, mag_binary, "Magnitude Gradient")
Direction Threshold¶
In [192]:
def dir_threshold(img, sobel_kernel=3, thresh=(0, np.pi/2)):
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
# Calculate the x and y gradients
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
# Take the absolute value of the gradient direction,
# apply a threshold, and create a binary image result
absgraddir = np.arctan2(np.absolute(sobely), np.absolute(sobelx))
binary_output = np.zeros_like(absgraddir)
binary_output[(absgraddir >= thresh[0]) & (absgraddir <= thresh[1])] = 1
return binary_output
image = cv2.imread('test_images/test6.jpg')
dir_binary = dir_threshold(image, sobel_kernel=15, thresh=(0.7, 1.3))
plot_threshold_gradient(image, dir_binary, "Direction Gradient")
Combined gradient¶
Now that we have 3 different types of gradients, let's combine them'
In [278]:
image = cv2.imread('test_images/test2.jpg')
#image = mpimg.imread('test_images/test3.jpg')
# Choose a Sobel kernel size
def combined_gradient(image):
ksize = 3 # Choose a larger odd number to smooth gradient measurements
# Apply each of the thresholding functions
gradx = abs_sobel_thresh(image, orient='x', sobel_kernel=ksize, thresh_min=20, thresh_max=110)
grady = abs_sobel_thresh(image, orient='y', sobel_kernel=ksize, thresh_min=20, thresh_max=110)
mag_binary = mag_thresh(image, sobel_kernel=ksize, mag_thresh=(30, 100))
dir_binary = dir_threshold(image, sobel_kernel=ksize, thresh=(0, np.pi/2))
combined = np.zeros_like(dir_binary)
combined[((gradx == 1) & (grady == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1
return combined
plot_threshold_gradient(image, combined_gradient(image), "Combined Gradient")
Color Threshold¶
I will come back to this
Perspective transform¶
Let us now create a perspective transform. We will use the straight lines images from the test directory in order to get the necessary trapezoid coordinates.
In [264]:
image = cv2.imread('test_images/straight_lines1.jpg')
#image = mpimg.imread('test_images/straight_lines1.jpg')
# 258, 50 -> lower left
# 603, 273 -> upper left
# 681, 273 -> upper right
# 1041, 50 -> lower right
# I used this section to select the points
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
plt.plot(258, 670, ".")
plt.plot(590, 450, ".")
plt.plot(690, 450, ".")
plt.plot(1041, 670, ".")
Out[264]:
In [234]:
src = np.float32([[258, 670],
[590, 450],
[690, 450],
[1041, 670]])
dst = np.float32([[258, 720],
[258, 0],
[1041, 0],
[1041, 720]])
# Define perspective transform funtion
def perspective_transform(img):
img_size = (img.shape[1], img.shape[0])
M = cv2.getPerspectiveTransform(src, dst)
Minv = cv2.getPerspectiveTransform(dst, src)
warped = cv2.warpPerspective(img, M, img_size, flags=cv2.INTER_LINEAR)
return warped
warped_im = perspective_transform(image)
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))
ax1.set_title = "Source Image"
ax1.imshow(image)
poly = plt.Polygon(src, closed=True, fill=False, color='#FF0000')
ax1.add_patch(poly)
ax2.set_title = "Warped Image"
ax2.imshow(warped_im)
poly = plt.Polygon(dst, closed=True, fill=False, color='#FF0000')
ax2.add_patch(poly)
Out[234]:
Let's see how this looks like on a a curved lane¶
In [267]:
image = mpimg.imread('test_images/test2.jpg')
warped_im = perspective_transform(image)
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))
ax1.set_title = "Source Image"
ax1.imshow(image)
poly = plt.Polygon(src, closed=True, fill=False, color='#FF0000')
ax1.add_patch(poly)
ax2.set_title = "Warped Image"
ax2.imshow(warped_im)
poly = plt.Polygon(dst, closed=True, fill=False, color='#FF0000')
ax2.add_patch(poly)
Out[267]:
Now let's apply this transform on an image with threshold¶
In [269]:
#image = cv2.imread('test_images/test6.jpg')
#image = mpimg.imread('test_images/test3.jpg')
# Choose a Sobel kernel size
ksize = 3 # Choose a larger odd number to smooth gradient measurements
# Apply each of the thresholding functions
gradx = abs_sobel_thresh(image, orient='x', sobel_kernel=ksize, thresh_min=20, thresh_max=110)
grady = abs_sobel_thresh(image, orient='y', sobel_kernel=ksize, thresh_min=20, thresh_max=110)
mag_binary = mag_thresh(image, sobel_kernel=ksize, mag_thresh=(30, 100))
dir_binary = dir_threshold(image, sobel_kernel=ksize, thresh=(0, np.pi/2))
combined = np.zeros_like(dir_binary)
combined[((gradx == 1) & (grady == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1
binary_warped = perspective_transform(combined)
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))
ax1.set_title = "Source Image"
ax1.imshow(image)
poly = plt.Polygon(src, closed=True, fill=False, color='#FF0000')
ax1.add_patch(poly)
ax2.set_title = "Warped Image"
ax2.imshow(binary_warped, cmap='gray')
poly = plt.Polygon(dst, closed=True, fill=False, color='#FF0000')
ax2.add_patch(poly)
Out[269]:
Now let us find the lanes!¶
We will be using a histogram to determine the intensity of the white pixels
In [270]:
histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)
plt.plot(histogram)
Out[270]:
In [271]:
# Assuming you have created a warped binary image called "binary_warped"
# Take a histogram of the bottom half of the image
histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)
# Create an output image to draw on and visualize the result
out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255
# Find the peak of the left and right halves of the histogram
# These will be the starting point for the left and right lines
midpoint = np.int(histogram.shape[0]//2)
leftx_base = np.argmax(histogram[:midpoint])
rightx_base = np.argmax(histogram[midpoint:]) + midpoint
# Choose the number of sliding windows
nwindows = 9
# Set height of windows
window_height = np.int(binary_warped.shape[0]//nwindows)
# Identify the x and y positions of all nonzero pixels in the image
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# Current positions to be updated for each window
leftx_current = leftx_base
rightx_current = rightx_base
# Set the width of the windows +/- margin
margin = 100
# Set minimum number of pixels found to recenter window
minpix = 50
# Create empty lists to receive left and right lane pixel indices
left_lane_inds = []
right_lane_inds = []
# Step through the windows one by one
for window in range(nwindows):
# Identify window boundaries in x and y (and right and left)
win_y_low = binary_warped.shape[0] - (window+1)*window_height
win_y_high = binary_warped.shape[0] - window*window_height
win_xleft_low = leftx_current - margin
win_xleft_high = leftx_current + margin
win_xright_low = rightx_current - margin
win_xright_high = rightx_current + margin
# Draw the windows on the visualization image
cv2.rectangle(out_img,(win_xleft_low,win_y_low),(win_xleft_high,win_y_high),
(0,255,0), 2)
cv2.rectangle(out_img,(win_xright_low,win_y_low),(win_xright_high,win_y_high),
(0,255,0), 2)
# Identify the nonzero pixels in x and y within the window
good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
(nonzerox >= win_xleft_low) & (nonzerox < win_xleft_high)).nonzero()[0]
good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
(nonzerox >= win_xright_low) & (nonzerox < win_xright_high)).nonzero()[0]
# Append these indices to the lists
left_lane_inds.append(good_left_inds)
right_lane_inds.append(good_right_inds)
# If you found > minpix pixels, recenter next window on their mean position
if len(good_left_inds) > minpix:
leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
if len(good_right_inds) > minpix:
rightx_current = np.int(np.mean(nonzerox[good_right_inds]))
# Concatenate the arrays of indices
left_lane_inds = np.concatenate(left_lane_inds)
right_lane_inds = np.concatenate(right_lane_inds)
# Extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds]
rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds]
# Fit a second order polynomial to each
left_fit = np.polyfit(lefty, leftx, 2)
right_fit = np.polyfit(righty, rightx, 2)
In [272]:
# Generate x and y values for plotting
ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]
out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]
plt.imshow(out_img)
plt.plot(left_fitx, ploty, color='yellow')
plt.plot(right_fitx, ploty, color='yellow')
plt.xlim(0, 1280)
plt.ylim(720, 0)
Out[272]:
In [273]:
# Assume you now have a new warped binary image
# from the next frame of video (also called "binary_warped")
# It's now much easier to find line pixels!
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
margin = 100
left_lane_inds = ((nonzerox > (left_fit[0]*(nonzeroy**2) + left_fit[1]*nonzeroy +
left_fit[2] - margin)) & (nonzerox < (left_fit[0]*(nonzeroy**2) +
left_fit[1]*nonzeroy + left_fit[2] + margin)))
right_lane_inds = ((nonzerox > (right_fit[0]*(nonzeroy**2) + right_fit[1]*nonzeroy +
right_fit[2] - margin)) & (nonzerox < (right_fit[0]*(nonzeroy**2) +
right_fit[1]*nonzeroy + right_fit[2] + margin)))
# Again, extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds]
rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds]
# Fit a second order polynomial to each
left_fit = np.polyfit(lefty, leftx, 2)
right_fit = np.polyfit(righty, rightx, 2)
# Generate x and y values for plotting
ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]
In [274]:
# Create an image to draw on and an image to show the selection window
out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255
window_img = np.zeros_like(out_img)
# Color in left and right line pixels
out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]
# Generate a polygon to illustrate the search window area
# And recast the x and y points into usable format for cv2.fillPoly()
left_line_window1 = np.array([np.transpose(np.vstack([left_fitx-margin, ploty]))])
left_line_window2 = np.array([np.flipud(np.transpose(np.vstack([left_fitx+margin,
ploty])))])
left_line_pts = np.hstack((left_line_window1, left_line_window2))
right_line_window1 = np.array([np.transpose(np.vstack([right_fitx-margin, ploty]))])
right_line_window2 = np.array([np.flipud(np.transpose(np.vstack([right_fitx+margin,
ploty])))])
right_line_pts = np.hstack((right_line_window1, right_line_window2))
# Draw the lane onto the warped blank image
cv2.fillPoly(window_img, np.int_([left_line_pts]), (0,255, 0))
cv2.fillPoly(window_img, np.int_([right_line_pts]), (0,255, 0))
result = cv2.addWeighted(out_img, 1, window_img, 0.3, 0)
plt.imshow(result)
plt.plot(left_fitx, ploty, color='yellow')
plt.plot(right_fitx, ploty, color='yellow')
plt.xlim(0, 1280)
plt.ylim(720, 0)
Out[274]:
In [276]:
# Create an image to draw the lines on
warp_zero = np.zeros_like(binary_warped).astype(np.uint8)
color_warp = np.dstack((warp_zero, warp_zero, warp_zero))
# Recast the x and y points into usable format for cv2.fillPoly()
pts_left = np.array([np.transpose(np.vstack([left_fitx, ploty]))])
pts_right = np.array([np.flipud(np.transpose(np.vstack([right_fitx, ploty])))])
pts = np.hstack((pts_left, pts_right))
# Draw the lane onto the warped blank image
cv2.fillPoly(color_warp, np.int_([pts]), (0,255, 0))
# Warp the blank back to original image space using inverse perspective matrix (Minv)
newwarp = cv2.warpPerspective(color_warp, Minv, (image.shape[1], image.shape[0]))
# Combine the result with the original image
result = cv2.addWeighted(image, 1, newwarp, 0.3, 0)
plt.imshow(result)
Out[276]:
Now let's create a pipeline and feed it multiple images¶
In [277]:
# Import everything needed to edit/save/watch video clips
from moviepy.editor import VideoFileClip
from IPython.display import HTML
In [284]:
# The final pipeline
def process_image(img):
combined_gradient_binary = combined_gradient(img)
binary_warped = perspective_transform(combined_gradient_binary)
# Assuming you have created a warped binary image called "binary_warped"
# Take a histogram of the bottom half of the image
histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)
# Create an output image to draw on and visualize the result
out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255
# Find the peak of the left and right halves of the histogram
# These will be the starting point for the left and right lines
midpoint = np.int(histogram.shape[0]//2)
leftx_base = np.argmax(histogram[:midpoint])
rightx_base = np.argmax(histogram[midpoint:]) + midpoint
# Choose the number of sliding windows
nwindows = 9
# Set height of windows
window_height = np.int(binary_warped.shape[0]//nwindows)
# Identify the x and y positions of all nonzero pixels in the image
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# Current positions to be updated for each window
leftx_current = leftx_base
rightx_current = rightx_base
# Set the width of the windows +/- margin
margin = 100
# Set minimum number of pixels found to recenter window
minpix = 50
# Create empty lists to receive left and right lane pixel indices
left_lane_inds = []
right_lane_inds = []
# Step through the windows one by one
for window in range(nwindows):
# Identify window boundaries in x and y (and right and left)
win_y_low = binary_warped.shape[0] - (window+1)*window_height
win_y_high = binary_warped.shape[0] - window*window_height
win_xleft_low = leftx_current - margin
win_xleft_high = leftx_current + margin
win_xright_low = rightx_current - margin
win_xright_high = rightx_current + margin
# Draw the windows on the visualization image
cv2.rectangle(out_img,(win_xleft_low,win_y_low),(win_xleft_high,win_y_high),
(0,255,0), 2)
cv2.rectangle(out_img,(win_xright_low,win_y_low),(win_xright_high,win_y_high),
(0,255,0), 2)
# Identify the nonzero pixels in x and y within the window
good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
(nonzerox >= win_xleft_low) & (nonzerox < win_xleft_high)).nonzero()[0]
good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) &
(nonzerox >= win_xright_low) & (nonzerox < win_xright_high)).nonzero()[0]
# Append these indices to the lists
left_lane_inds.append(good_left_inds)
right_lane_inds.append(good_right_inds)
# If you found > minpix pixels, recenter next window on their mean position
if len(good_left_inds) > minpix:
leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
if len(good_right_inds) > minpix:
rightx_current = np.int(np.mean(nonzerox[good_right_inds]))
# Concatenate the arrays of indices
left_lane_inds = np.concatenate(left_lane_inds)
right_lane_inds = np.concatenate(right_lane_inds)
# Extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds]
rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds]
# Fit a second order polynomial to each
left_fit = np.polyfit(lefty, leftx, 2)
right_fit = np.polyfit(righty, rightx, 2)
# Assume you now have a new warped binary image
# from the next frame of video (also called "binary_warped")
# It's now much easier to find line pixels!
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
margin = 100
left_lane_inds = ((nonzerox > (left_fit[0]*(nonzeroy**2) + left_fit[1]*nonzeroy +
left_fit[2] - margin)) & (nonzerox < (left_fit[0]*(nonzeroy**2) +
left_fit[1]*nonzeroy + left_fit[2] + margin)))
right_lane_inds = ((nonzerox > (right_fit[0]*(nonzeroy**2) + right_fit[1]*nonzeroy +
right_fit[2] - margin)) & (nonzerox < (right_fit[0]*(nonzeroy**2) +
right_fit[1]*nonzeroy + right_fit[2] + margin)))
# Again, extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds]
rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds]
# Fit a second order polynomial to each
left_fit = np.polyfit(lefty, leftx, 2)
right_fit = np.polyfit(righty, rightx, 2)
# Generate x and y values for plotting
ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]
# Create an image to draw on and an image to show the selection window
out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255
window_img = np.zeros_like(out_img)
# Color in left and right line pixels
out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]
# Generate a polygon to illustrate the search window area
# And recast the x and y points into usable format for cv2.fillPoly()
left_line_window1 = np.array([np.transpose(np.vstack([left_fitx-margin, ploty]))])
left_line_window2 = np.array([np.flipud(np.transpose(np.vstack([left_fitx+margin,
ploty])))])
left_line_pts = np.hstack((left_line_window1, left_line_window2))
right_line_window1 = np.array([np.transpose(np.vstack([right_fitx-margin, ploty]))])
right_line_window2 = np.array([np.flipud(np.transpose(np.vstack([right_fitx+margin,
ploty])))])
right_line_pts = np.hstack((right_line_window1, right_line_window2))
# Draw the lane onto the warped blank image
cv2.fillPoly(window_img, np.int_([left_line_pts]), (0,255, 0))
cv2.fillPoly(window_img, np.int_([right_line_pts]), (0,255, 0))
result = cv2.addWeighted(out_img, 1, window_img, 0.3, 0)
# Create an image to draw the lines on
warp_zero = np.zeros_like(binary_warped).astype(np.uint8)
color_warp = np.dstack((warp_zero, warp_zero, warp_zero))
# Recast the x and y points into usable format for cv2.fillPoly()
pts_left = np.array([np.transpose(np.vstack([left_fitx, ploty]))])
pts_right = np.array([np.flipud(np.transpose(np.vstack([right_fitx, ploty])))])
pts = np.hstack((pts_left, pts_right))
# Draw the lane onto the warped blank image
cv2.fillPoly(color_warp, np.int_([pts]), (0,255, 0))
# Warp the blank back to original image space using inverse perspective matrix (Minv)
newwarp = cv2.warpPerspective(color_warp, Minv, (img.shape[1], img.shape[0]))
# Combine the result with the original image
result = cv2.addWeighted(img, 1, newwarp, 0.3, 0)
return result
# Make a list of calibration images
images = glob.glob('test_images/*.jpg')
images_with_lane_marking = []
# Step through the list and search for chessboard corners
for fname in images:
img = cv2.imread(fname)
images_with_lane_marking.append(process_image(img))
In [286]:
plt.figure(figsize=(50,30))
columns = 4
for i, image in enumerate(images_with_lane_marking):
plt.subplot(len(images_with_lane_marking) / columns + 1, columns, i + 1)
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
Now let's record the video!¶
In [289]:
white_output = 'test_videos_output/project_video_result.mp4'
#clip1 = VideoFileClip("project_video.mp4").subclip(0,5)
clip1 = VideoFileClip("project_video.mp4")
white_clip = clip1.fl_image(process_image) #NOTE: this function expects color images!!
%time white_clip.write_videofile(white_output, audio=False)